RIVET: Robust Idempotent Voice Attribute Editing

• URL: http://arxiv.org/abs/2606.19629v1
• Date: Wed, 17 Jun 2026 22:16:13 GMT
• Title: RIVET: Robust Idempotent Voice Attribute Editing
• Abstract summary: We show that idempotency provides an effective mechanism for improving robustness to noisy labels.<n>We introduce RIVET, a training framework that incorporates an idempotency objective to improve robustness to label noise.<n> RIVET improves editing success and better preserves attribute identity than standard training, showing that idempotency improves robustness in voice editing models.
• Score: 59.80556306916532
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Voice attribute editing models modify characteristics such as age and gender while preserving speaker identity. In large-scale speech datasets, however, attribute annotations are often noisy or inconsistent, which can cause conditional generative models to produce unstable edits. In this work, we show that idempotency provides an effective mechanism for improving robustness to noisy labels. An idempotent operator is one for which repeated application does not change the result, i.e., f(f(x)) = f(x). Enforcing this property acts as an implicit regularizer that reduces sensitivity to mislabeled examples. We introduce RIVET, a training framework that incorporates an idempotency objective to improve robustness to label noise. We evaluate RIVET under controlled label noise and on the GLOBE dataset with naturally noisy annotations. RIVET improves editing success and better preserves speaker identity than standard training, showing that idempotency improves robustness in voice editing models.

Related papers

• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models [12.527207210862151]
  ReHear is a framework for iterative pseudo-label refinement in automatic speech recognition.<n>It integrates an instruction-tuned, audio-aware large language model into the self-training loop.<n>We show that ReHear effectively mitigates error propagation, consistently outperforming both supervised and pseudo-labeling baselines.
  arXiv  Detail & Related papers  (2026-02-21T05:04:22Z)
• Residual Tokens Enhance Masked Autoencoders for Speech Modeling [31.12667739896418]
  We introduce RT-MAE, a novel masked autoencoder framework that augments the supervised attributes-based modeling with unsupervised residual trainable tokens.<n> Experiments show that RT-MAE improves reconstruction quality, preserving content and speaker similarity while enhancing expressivity.
  arXiv  Detail & Related papers  (2026-01-27T09:30:31Z)
• BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition [63.45645200463539]
  BiRQ is a bilevel SSL framework that combines the efficiency of BEST-RQ with the refinement benefits of HuBERT-style label enhancement.<n>We validate our method on various datasets, including 960-hour LibriSpeech, 150-hour AMI meetings and 5,000-hour YODAS.
  arXiv  Detail & Related papers  (2025-09-18T21:09:29Z)
• Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labels [18.868523370902338]
  We propose a Mean Teacher-based Adaptive Label Correction framework for robust medical image segmentation with noisy labels.<n>It includes an adaptive label refinement mechanism that dynamically captures and weights differences across multiple disturbance versions to enhance the quality of noisy labels.<n>It also incorporates a sample-level uncertainty-based label selection algorithm to prioritize high-confidence samples for network updates.
  arXiv  Detail & Related papers  (2025-03-15T18:03:01Z)
• Mitigating Instance-Dependent Label Noise: Integrating Self-Supervised Pretraining with Pseudo-Label Refinement [3.272177633069322]
  Real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.<n>We propose a novel framework that combines self-supervised learning using SimCLR with iterative pseudo-label refinement.<n>Our approach significantly outperforms several state-of-the-art methods, particularly under high noise conditions.
  arXiv  Detail & Related papers  (2024-12-06T09:56:49Z)
• Can We Treat Noisy Labels as Accurate? [87.23815842898722]
  Noisy labels significantly hinder the accuracy and generalization of machine learning models.<n>We propose EchoAlign, a paradigm shift in learning from noisy labels.<n>Under 30% instance-dependent noise, EchoSelect retains nearly twice the number of correctly labeled samples compared to previous methods.
  arXiv  Detail & Related papers  (2024-05-21T17:49:10Z)
• Learning to Detect Noisy Labels Using Model-Based Features [16.681748918518075]
  We propose Selection-Enhanced Noisy label Training (SENT) SENT does not rely on meta learning while having the flexibility of being data-driven. It improves performance over strong baselines under the settings of self-training and label corruption.
  arXiv  Detail & Related papers  (2022-12-28T10:12:13Z)
• Instance-dependent Label-noise Learning under a Structural Causal Model [92.76400590283448]
  Label noise will degenerate the performance of deep learning algorithms. By leveraging a structural causal model, we propose a novel generative approach for instance-dependent label-noise learning.
  arXiv  Detail & Related papers  (2021-09-07T10:42:54Z)
• Approximating Instance-Dependent Noise via Instance-Confidence Embedding [87.65718705642819]
  Label noise in multiclass classification is a major obstacle to the deployment of learning systems. We investigate the instance-dependent noise (IDN) model and propose an efficient approximation of IDN to capture the instance-specific label corruption.
  arXiv  Detail & Related papers  (2021-03-25T02:33:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.